Papers with Code 아카이브

Mixture-of-Experts

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/bartwojcik/sadmoe

공식 코드

Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion

https://github.com/batistagroup/DirectMultiStep

공식 코드

DirectMultiStep: Direct Route Generation for Multi-Step Retrosynthesis

https://github.com/bigyehahaha/m4

공식 코드

M4: Multi-Proxy Multi-Gate Mixture of Experts Network for Multiple Instance Learning in Histopathology Image Analysis

https://github.com/binging512/umpsnet

공식 코드

A Multi-Modal Deep Learning Framework for Pan-Cancer Prognosis

https://github.com/brushing-git/peircemachine

공식 코드

Peirce in the Machine: How Mixture of Experts Models Perform Hypothesis Construction

https://github.com/bu-cisl/DynamicSyntesisNetwork

공식 코드

Adaptive 3D descattering with a dynamic synthesis network

https://github.com/budzianowski/multiwoz

공식 코드

A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Experts

https://github.com/bumble666/hypermoe_early_version

공식 코드

HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts

https://github.com/buraksatar/RoME_video_retrieval

공식 코드

RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval

https://github.com/byeongjun-park/Switch-DiT

공식 코드

Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts

https://github.com/bytedance/flux

공식 코드

Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts

https://github.com/cat538/mxmoe

공식 코드

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

https://github.com/celin-yao/da-moe

공식 코드

DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts

https://github.com/cengzihao/adamoe

공식 코드

AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models

https://github.com/checkstep/mole-stance

공식 코드

Cross-Domain Label-Adaptive Stance Detection

https://github.com/clovaai/FocusSeq2Seq

공식 코드

Mixture Content Selection for Diverse Sequence Generation

https://github.com/cmu-flame/flame-moe

공식 코드

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models

https://github.com/cocowy1/smoe-stereo

공식 코드

Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts

https://github.com/codecaution/evomoe

공식 코드

EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate

https://github.com/copenlu/xformer-multi-source-domain-adaptation

공식 코드

Transformer Based Multi-Source Domain Adaptation

https://github.com/cschenxiang/drsformer

공식 코드

Learning A Sparse Transformer Network for Effective Image Deraining

https://github.com/csguoh/adaptir

공식 코드

Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts

https://github.com/csjliang/dasr

공식 코드

Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution

https://github.com/currentf/meft

공식 코드

MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter

https://github.com/d909b/ame

공식 코드

Granger-causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks

https://github.com/daizedong/unified-moe-compression

공식 코드

Demystifying the Compression of Mixture-of-Experts Through a Unified Framework

https://github.com/dannis97500/pm-moe

공식 코드

PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning

https://github.com/davidfanzz/scmoe

공식 코드

Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast

https://github.com/dawnvince/mts_cad

공식 코드

Beyond Sharing: Conflict-Aware Multivariate Time Series Anomaly Detection

https://github.com/ddidacus/mol-moe

공식 코드

Mol-MoE: Training Preference-Guided Routers for Molecule Generation

https://github.com/deepseek-ai/DeepEP

공식 코드

A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications

https://github.com/deepseek-ai/deepseek-coder-v2

공식 코드

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

https://github.com/deepseek-ai/deepseek-moe

공식 코드

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

https://github.com/deepseek-ai/deepseek-v2

공식 코드

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

https://github.com/deepseek-ai/deepseek-v3

공식 코드

DeepSeek-V3 Technical Report

https://github.com/deepseek-ai/deepseek-vl2

공식 코드

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.